Ultrasonic plane wave composite imaging method and device and storage medium

Abstract

The invention provides an ultrasonic plane wave imaging method and device and a storage medium. The method comprises the steps: processing a natural image; obtaining ultrasonic simulation images whichare similar to real ultrasonic images and are large in number, training a deep learning network by utilizing the massive ultrasonic simulation images, and applying a training model meeting conditionsto a real small-scale ultrasonic data set for transfer learning to obtain a practical model with strong robustness and high generalization; employing low-quality plane wave ultrasonic images at threeangles, and directly generating an ultrasonic image which is consistent with or even higher than an image obtained through multi-angle composite imaging in quality through a trained deep learning network, thereby keeping the advantages that the plane wave ultrasonic imaging speed is high and the frame rate is high to the maximum extent. The problems that in an existing ultrasonic plane wave imaging method based on deep learning, training data are few, an over-fitting phenomenon exists, and a practical model high in robustness and generalization cannot be obtained are solved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular, to an ultrasonic plane wave composite imaging method, device and storage medium. Background technique [0002] The ultrasound equipment emits plane waves at different angles, and the ultrasound signals collected at each angle are combined to generate an ultrasound image. Although ultrasonic plane wave imaging has an ultra-high-speed imaging frame rate, the quality of ultrasonic images obtained through a single angle is low because ultrasonic plane waves are not focused. Multi-angle compound imaging can improve image quality by spatially compounding ultrasound images from multiple angles, but significantly reduces the imaging frame rate. Therefore, it is of great significance to improve the image quality and maintain the imaging frame rate through image processing or deep learning methods, which is of great significance for the ultrafast imaging required in clinica...

AI Technical Summary

Problems solved by technology

It solves the problem that the current ultrasonic plane wave imaging method based on deep learning has little training data and overfitting phenomenon, and it is impossible to obtain a practical model with strong robustness and high generalization

Images